my_library

16,958 bookmarks · page 21 of 340
2026-03-30 · substack.com

Language Birth

Since 1960, the world has lost hundreds of languages — and gained thousands.

Toki Pona has only 120 words. None of them change form, in any way, in any context. The grammar is nearly the bare minimum — specified word order, and a few particles to denote a predicate, a direct object, subordination, negation. Interpreting any utterance takes a lot of context clues, or a lot…
2026-03-28 · blog.dailydoseofds.com

Anatomy of the .claude/ Folder

A complete guide to CLAUDE.md, custom commands, skills, agents, and permissions, and how to set them up properly.

2026-03-28 · open.substack.com

Metannoying

Your brain on "not X but Y"

This happens in seconds. A student with high verbal aptitude processes this almost instantaneously.
Psychometricians have called antonyms the most efficient measure of verbal intelligence in the toolkit: high g-loading, high discrimination at the top of the ability range, no contextual scaffolding.
2026-03-23 · artofmanliness.com

An Average Joe's Guide to HVAC | The Art of Manliness

Back in January, a day before a big winter freeze was about to hit Tulsa and dump a foot of snow on us, our home’s furnace stopped working. I didn’t want to spend a week without heat, so I called an HVAC (Heating, Ventilation, and Air Conditioning) company. The technician who…

2026-03-23 · marktechpost.com

How BM25 and RAG Retrieve Information Differently? - MarkTechPost

When you type a query into a search engine, something has to decide which documents are actually relevant — and how to rank them. BM25 (Best Matching 25), the algorithm powering search engines like Elasticsearch and Lucene, has been the dominant answer to that question for…

The clever part is that BM25 doesn’t reward keyword stuffing
saturation
2026-03-23 · simonwillison.net

Research: Starlette 1.0 skill

Starlette 1.0 Skill offers a concise guide for building robust web applications with Starlette, a lightweight ASGI framework. The accompanying demo showcases a task management app featuring projects, tasks, comments, …

2026-03-22 · techcrunch.com

An exclusive tour of Amazon’s Trainium lab, the chip that’s won over Anthropic, OpenAI, even Apple

Shortly after Amazon announced its $50 billion investment in OpenAI, AWS invited me on a private tour of the chip lab at the heart of the deal.

Note: Based on the article **[An exclusive tour of Amazon’s Trainium lab, the chip that’s won over Anthropic, OpenAI, even Apple](#rid:1653401870)**, here are the key points: ### Strategic Impact & Partnerships * **Major Adoption:** Amazon’s custom chips have secured massive commitments from leading AI labs. **Anthropic** runs Claude on over 1 million Trainium2 chips, and **OpenAI** recently signed a…

2026-03-22 · marktechpost.com

Safely Deploying ML Models to Production: Four Controlled Strategies (A/B, Canary, Interleaved, Shadow Testing) - MarkTechPost

Safely Deploying Machine Learning Models to Production: Four Controlled Strategies (A/B, Canary, Interleaved, Shadow Testing)

Note: This bookmark, **[Safely Deploying ML Models to Production: Four Controlled Strategies](#rid:1652757915)**, is an article from MarkTechPost that outlines how to release machine learning models into production while minimizing risk. The article details four key deployment strategies: * **A/B Testing**: Randomly splits a small percentage of total traffic to the new model while the rest stays on the…

2026-03-21 · sebastianraschka.com

LLM Architecture Gallery

A gallery that collects architecture figures from The Big LLM Architecture Comparison and related articles, with fact sheets and links back to the original sections.